Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "Nick Cox" <n.j.cox@durham.ac.uk> |
| To | <statalist@hsphsun2.harvard.edu> |
| Subject | st: RE: chi-square-test in matrix or crosstab |
| Date | Fri, 18 Jun 2010 11:47:52 +0100 |
Not quite clear about your set-up, but -tab_chi- on SSC contains various immediate commands which go a bit beyond official -tabi-. Nick n.j.cox@durham.ac.uk Wetzel Martin I'm looking for a opportunity to make chi-square-tests of already acummulated data. I have something like this sysuse auto.dta, clear tab2 rep78 foreign, matcell(A) matrix list A and now I want to test this matrix for statistical independence. If the matrix would always have the same size, I could use William Gould's (2006)* mata-strategy, but it's looped over vars, so I could need a more flexible way. Has anyone an idea? * Gould (2006): Mata Matters: Interactive use. The Stata Journal 6 (3). pp. 387-396. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/